Railway foundation settlement management early warning method and system

Abstract

The invention is suitable for the field of railway foundation management, and provides a railway foundation settlement management early warning method and system, and the method comprises the steps: installing a vehicle-mounted displacement sensor at a target position of a driving vehicle; continuously distributed optical fiber sensing monitor groups and temperature sensors are deployed in the railway line; establishing a space-time synchronous calibration model of the vehicle-mounted displacement sensor and the optical fiber sensing network, performing fusion processing on vehicle body longitudinal displacement data acquired in real time and optical fiber strain data of a corresponding mileage segment, and calculating the longitudinal change degree of a foundation in a monitoring interval; setting a multi-level threshold triggering and rechecking strategy; multi-source data are fused, and a stepped intelligent early warning notification is generated and sent based on a multi-level threshold triggering and rechecking strategy; according to the method, a train-line-foundation three-in-one intelligent monitoring system is constructed, and the temporal-spatial resolution and accuracy of railway foundation settlement monitoring are remarkably improved. A multi-level threshold and recheck mechanism reduces the false alarm and missing alarm rate, and stepped early warning realizes risk hierarchical management and control.

Description

Technical Field

[0001] The present invention belongs to the field of railway foundation management, and in particular relates to a railway foundation settlement management early warning method and system. Background Art

[0002] Railway foundation settlement monitoring is a key technology for ensuring safe train operation. Existing monitoring methods primarily rely on fixed-point sensors or distributed fiber optic sensing systems. However, traditional point-based monitoring suffers from insufficient spatial resolution and difficulty capturing localized sudden changes in settlement. While purely distributed fiber optic monitoring enables continuous measurement, it is limited by the long distances of railway lines and exhibits a time lag in the instantaneous response to settlement under dynamic vehicle loads.

[0003] Furthermore, existing technologies lack the ability to couple dynamic vehicle displacement with static subgrade settlement, making them unable to accurately identify abnormal longitudinal vehicle displacement caused by uneven subgrade settlement during vehicle operation. This can easily lead to missed detections or false alarms, making it difficult to meet the real-time millimeter-level settlement monitoring requirements of high-speed rail operations. To address the issues of delayed dynamic load response and insufficient multi-source data fusion in existing technologies, a more mature railway subgrade settlement management and early warning method and system is urgently needed. Summary of the Invention

[0004] The purpose of the present invention is to provide a railway foundation settlement management early warning method and system, aiming to solve the problems raised in the above background technology.

[0005] The present invention is implemented as follows: on the one hand, a railway foundation settlement management and early warning method, the method comprising:

[0006] Installing on-board displacement sensors at targeted locations on the moving vehicle to collect real-time longitudinal displacement data of the vehicle body during driving. The targeted locations include the bogie axle box, the central section of the vehicle body underframe, and the vehicle body directly above the rail contact surface;

[0007] Deploy a continuous distributed optical fiber sensor monitor group and temperature sensors within the railway line to collect continuous strain distribution data and temperature data of the railway foundation in real time. The continuous distributed optical fiber sensor monitor group includes an optical fiber sensor network laid along the railway line;

[0008] A spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the fiber optic sensing network is established. The real-time collected vehicle body longitudinal displacement data is fused with the fiber optic strain data of the corresponding mileage segment to calculate the longitudinal change degree of the foundation within the monitoring interval.

[0009] Set up multi-level threshold triggering and rechecking strategies;

[0010] By integrating multi-source data and based on multi-level threshold triggering and re-inspection strategies, it generates and sends stepped intelligent early warning notifications.

[0011] As a further solution of the present invention, the establishment of a spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the optical fiber sensing network, fusing the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage segment, and calculating the longitudinal change degree of the foundation within the monitoring interval specifically includes:

[0012] Establish a spatiotemporal mapping relationship based on the GPS timestamps on the vehicles and the mileage marks on the routes;

[0013] The vehicle displacement data is de-noised using the Kalman filter algorithm, and the optical fiber strain data is temperature compensated simultaneously;

[0014] The compensated optical fiber strain value The calculation process is:

[0015] ;

[0016] Where, is the original optical fiber strain measurement value without temperature compensation, is the thermal expansion coefficient of the optical fiber, is the real-time temperature change.

[0017] As a further embodiment of the present invention, the establishment of a spatiotemporal synchronization calibration model between the vehicle-mounted displacement sensor and the optical fiber sensor network, the fusion processing of the real-time collected vehicle body longitudinal displacement data and the optical fiber strain data of the corresponding mileage segment, and the calculation of the longitudinal change degree of the foundation within the monitoring interval specifically include:

[0018] Based on the dynamic time warping algorithm, the vehicle longitudinal displacement curve is phase-aligned with the optical fiber strain curve of the corresponding mileage segment;

[0019] Based on the differential algorithm, the longitudinal deformation gradient value of the foundation within the monitoring area is calculated ;

[0020] The longitudinal deformation gradient value of the foundation The calculation process is:

[0021] ;

[0022] Where, For the The longitudinal deformation gradient of the monitoring surface, is the longitudinal displacement of the vehicle-mounted sensor in the corresponding section, is the cross-section spacing, Vertical strain-converted displacement calculated for the fiber optic sensing monitor set.

[0023] As a further solution of the present invention, the setting of multi-level threshold triggering and rechecking strategy specifically includes:

[0024] Two levels of longitudinal change thresholds are preset, the primary change threshold is , the emergency change threshold is ;

[0025] When the longitudinal deformation gradient value of the foundation is Exceeding the primary change threshold When the regional level re-inspection instruction is triggered;

[0026] Based on the regional re-inspection instructions, the fiber optic static level sensor group deployed in the monitoring section is controlled to measure the pressure changes of each reference point in real time through the liquid level connecting pipe;

[0027] Calculate the relative settlement of each benchmark point ;

[0028] The relative settlement The calculation process is:

[0029] ;

[0030] Where, is the pressure change value, is the density of the connecting fluid, Take 9.81 ;

[0031] When the foundation longitudinal deformation gradient value Exceeding the emergency change threshold , triggering full-line-level real-time scanning.

[0032] As a further solution of the present invention, the fusion of multi-source data, based on multi-level threshold triggering and re-inspection strategy, generates and sends a step-by-step intelligent early warning notification, specifically including:

[0033] Construct a fusion warning model including a back-propagation neural network. The input parameters of the fusion warning model include: vehicle longitudinal displacement, optical fiber strain value, liquid level pressure change rate, ambient temperature and humidity, and train speed;

[0034] When the relative settlement of any benchmark point When the target threshold is exceeded, a step-by-step warning signal is generated and a ballastless section threshold is set. , ballasted section threshold ;

[0035] In ballastless sections, the stepped warning signals include:

[0036] Yellow alert: Generate and send manual inspection instructions;

[0037] Orange alert: When , a speed reduction instruction is generated and sent;

[0038] Orange alert: Generate and send an emergency stop command.

[0039] As a further embodiment of the present invention, in another aspect, a railway foundation settlement management and early warning system is provided, the system comprising:

[0040] The first real-time acquisition module is used to install a vehicle-mounted displacement sensor at a target position of a moving vehicle to collect the longitudinal displacement data of the vehicle body in real time during the vehicle's driving process;

[0041] The target locations include the bogie axle box, the central section of the car body underframe, and the car body just above the rail contact surface;

[0042] The second real-time acquisition module is used to deploy a continuous distributed optical fiber sensor monitor group and temperature sensors within the railway line to collect continuous strain distribution data and temperature data of the railway foundation in real time;

[0043] The continuous distributed optical fiber sensor monitor group includes an optical fiber sensor network laid along the railway line;

[0044] The spatiotemporal synchronization calibration model module is used to establish a spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the optical fiber sensing network;

[0045] The calculation module is used to integrate the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage section to calculate the longitudinal change degree of the foundation within the monitoring area;

[0046] The control module is used to set multi-level threshold triggers and re-inspection strategies;

[0047] Generate and send modules to integrate multi-source data, generate and send step-by-step intelligent early warning notifications based on multi-level threshold triggering and re-inspection strategies.

[0048] As a further solution of the present invention, the spatiotemporal synchronization calibration model module specifically includes:

[0049] A mapping unit, configured to establish a spatiotemporal mapping relationship based on a GPS time stamp of a traveling vehicle and a mileage mark of a route;

[0050] The synchronous compensation unit is used to perform denoising on the vehicle displacement data through the Kalman filter algorithm and synchronously perform temperature compensation on the optical fiber strain data.

[0051] As a further solution of the present invention, the calculation module includes:

[0052] Phase alignment unit, used to align the vehicle longitudinal displacement curve with the optical fiber strain curve of the corresponding mileage segment based on the dynamic time warping algorithm;

[0053] The first calculation unit is used to calculate the longitudinal deformation gradient value of the foundation within the monitoring interval based on the differential algorithm .

[0054] As a further solution of the present invention, the control module specifically includes:

[0055] A two-level longitudinal change degree threshold unit is used to preset two-level longitudinal change degree thresholds;

[0056] Recheck unit, used for the longitudinal deformation gradient value of the foundation for three consecutive sampling periods Exceeding the primary change threshold When the regional level re-inspection instruction is triggered;

[0057] The real-time measurement unit is used to control the fiber optic static level sensor group deployed in the monitoring section based on the regional re-inspection instructions, and measure the pressure changes of each reference point in real time through the liquid level connecting pipe;

[0058] The second calculation unit is used to calculate the relative settlement of each benchmark point ;

[0059] Full-line real-time scanning unit, used to measure the longitudinal deformation gradient value of the local foundation Exceeding the emergency change threshold , triggering full-line-level real-time scanning.

[0060] As a further solution of the present invention, the generating and sending module specifically includes:

[0061] A fusion warning model unit, used to construct a fusion warning model including a back-propagation neural network;

[0062] The input parameters of the fusion warning model include: vehicle longitudinal displacement, optical fiber strain value, liquid level pressure change rate, ambient temperature and humidity, and train speed;

[0063] Generate units for relative settlement of any benchmark point When the target threshold is exceeded, a stepped warning signal is generated.

[0064] This invention provides a railway foundation settlement management and early warning method and system. This method and system establish a three-in-one intelligent monitoring system for "train, track, and foundation," significantly improving the temporal and spatial resolution and accuracy of railway foundation settlement monitoring. A multi-level threshold and recheck mechanism reduces false alarms and missed alarms, while a stepped early warning system enables tiered risk management and control, effectively ensuring train operation safety. The intelligent early warning system integrates railway dispatching and operations and maintenance, improving emergency response efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a main flow chart of a railway foundation settlement management and early warning method.

[0066] Figure 2 The present invention is a flow chart of the first embodiment of a railway foundation settlement management and early warning method, which establishes a spatiotemporal synchronization calibration model between a vehicle-mounted displacement sensor and a fiber optic sensing network, fuses the real-time collected vehicle body longitudinal displacement data with the fiber optic strain data of the corresponding mileage section, and calculates the longitudinal change degree of the foundation within the monitoring interval.

[0067] Figure 3 The present invention is a flow chart of the second embodiment of a railway foundation settlement management and early warning method, which establishes a spatiotemporal synchronization calibration model between the vehicle-mounted displacement sensor and the optical fiber sensing network, fuses the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage section, and calculates the longitudinal change degree of the foundation within the monitoring interval.

[0068] Figure 4 The present invention is a flow chart of setting a multi-level threshold trigger and recheck strategy in a railway foundation settlement management early warning method.

[0069] Figure 5 The invention relates to a method for railway foundation settlement management and early warning, which integrates multi-source data and generates and sends a step-by-step intelligent early warning notification based on a multi-level threshold trigger and re-inspection strategy.

[0070] Figure 6 It is a main structural diagram of a railway foundation settlement management and early warning system.

[0071] Figure 7 The present invention is a structural block diagram of a spatiotemporal synchronization calibration model module in a railway foundation settlement management and early warning system.

[0072] Figure 8 It is a structural block diagram of the calculation module in the railway foundation settlement management and early warning system.

[0073] Figure 9 It is a structural block diagram of the control module in the railway foundation settlement management and early warning system.

[0074] Figure 10 The present invention is a structural block diagram of a generation and sending module in a railway foundation settlement management and early warning system. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0076] The specific implementation of the present invention is described in detail below with reference to specific embodiments.

[0077] The present invention provides a railway foundation settlement management and early warning method and system, which solves the technical problems in the background technology.

[0078] like Figure 1 FIG. 1 is a main flow chart of a railway foundation settlement management and early warning method provided by an embodiment of the present invention. The railway foundation settlement management and early warning method includes:

[0079] Step S100: installing a vehicle-mounted displacement sensor at a target position of a moving vehicle to collect longitudinal displacement data of the vehicle body in real time during the vehicle's travel;

[0080] The target locations include the bogie axle box, the central section of the car body underframe, and the car body just above the rail contact surface;

[0081] Step S200: deploying a continuous distributed optical fiber sensor monitor group and a temperature sensor in the railway line to collect continuous strain distribution data and temperature data of the railway foundation in real time;

[0082] The continuous distributed optical fiber sensor monitor group includes an optical fiber sensor network laid along the railway line;

[0083] Step S300: Establishing a spatiotemporal synchronization calibration model between the vehicle-mounted displacement sensor and the optical fiber sensing network, fusing the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage segment, and calculating the longitudinal change degree of the foundation within the monitoring interval;

[0084] Step S400: Setting a multi-level threshold trigger and recheck strategy;

[0085] Step S500: Fusing multi-source data, generating and sending a step-by-step intelligent early warning notification based on multi-level threshold triggering and re-inspection strategies;

[0086] In this embodiment, the present invention constructs a three-in-one intelligent monitoring system for "vehicle-line-foundation." At the data acquisition level, high-precision onboard displacement sensors are precisely installed on the bogie axlebox, the central section of the car body underframe, and the car body directly above the rail contact surface. These sensors, comprising a MEMS inertial measurement unit with a sampling frequency of ≥100Hz and a Beidou differential positioning module with centimeter-level accuracy, capture vehicle longitudinal displacement, pitch angle, and acceleration data in real time at a high-frequency interval of ≤50ms, accurately reflecting the dynamic response of the vehicle during operation. Simultaneously, two single-mode optical fibers are laid parallel to each other at a depth of 0.3-0.5m below the roadbed on both sides of the railway line, forming a distributed fiber optic sensing network with a spacing of 50-100m. Leveraging BOTDA technology, this network enables continuous strain data acquisition with a spatial resolution of ≤1m, comprehensively capturing ground condition information and eliminating temperature interference on fiber optic strain measurements. In the data processing and analysis stage, a spatiotemporal synchronization calibration model is established based on the vehicle-mounted GPS timestamp and line mileage marks. The Kalman filter algorithm is used to denoise the vehicle-mounted displacement data, and the dynamic time warping algorithm is used to align the phase of the vehicle-mounted longitudinal displacement curve with the optical fiber strain curve. The longitudinal change degree of the foundation within the monitoring interval is calculated to achieve deep fusion of vehicle-ground data, and two-level longitudinal change degree thresholds and corresponding regional and full-line re-inspection strategies are set. The relative settlement is calculated based on the principle of liquid column balance in the connecting tube through the optical fiber static level sensor group; a multi-source data fusion early warning model is constructed based on the BP neural network, and a coupling analysis is performed on multiple parameters such as the vehicle-mounted longitudinal displacement, optical fiber strain value, and liquid level pressure change rate. According to the different safety thresholds of ballastless and ballasted tracks, three-level stepped early warning signals of yellow, orange, and red are generated, and the railway dispatching and operation and maintenance systems are linked to realize intelligent management of the entire process from monitoring to disposal.

[0087] like Figure 2 As shown in FIG. , as a preferred embodiment of the present invention, the establishment of a spatiotemporal synchronization calibration model between the vehicle-mounted displacement sensor and the optical fiber sensing network, the fusion processing of the real-time collected vehicle body longitudinal displacement data and the optical fiber strain data of the corresponding mileage segment, and the calculation of the longitudinal change degree of the foundation within the monitoring interval specifically include:

[0088] Step S301: establishing a spatiotemporal mapping relationship based on the GPS timestamp of the traveling vehicle and the mileage mark of the route;

[0089] Step S302: De-noising the vehicle displacement data using a Kalman filter algorithm, and simultaneously performing temperature compensation on the optical fiber strain data;

[0090] The compensated optical fiber strain value The calculation process is:

[0091] ;

[0092] Where, is the original optical fiber strain measurement value without temperature compensation, is the thermal expansion coefficient of the optical fiber, is the real-time temperature change;

[0093] When this embodiment is applied, a spatiotemporal mapping relationship is established using the GPS timestamps on the moving vehicle and the line mileage markers. While the vehicle is driving, the on-board GPS can accurately record the vehicle's position at different times, while the line mileage markers clearly define the mileage information of each location on the railway line. By combining the two, the data collected on the vehicle can be accurately mapped to the specific location and time point of the railway line. The Kalman filter algorithm is then used to denoise the on-board displacement data. Since the on-board displacement sensor is affected by factors such as vibration and electromagnetic interference during the vehicle's driving process when collecting data, the data contains noise. The Kalman filter algorithm can make an optimal estimate of the data based on the historical information and current measurement values ​​of the data, effectively remove noise interference, and make the on-board displacement data more accurate and reliable. At the same time, the optical fiber strain data is temperature compensated. Fiber optic strain data will be affected by changes in ambient temperature. Temperature changes will cause the optical fiber to expand and contract, thereby affecting the strain measurement results. The data after time-space mapping, denoising and temperature compensation processing provides data support for the subsequent use of dynamic time warping algorithms to align the phase of the vehicle-mounted longitudinal displacement curve with the fiber optic strain curve, and to calculate the degree of longitudinal change of the foundation within the monitoring area.

[0094] like Figure 3 As shown, as a preferred embodiment of the present invention, the establishment of a spatiotemporal synchronization calibration model between the vehicle-mounted displacement sensor and the optical fiber sensing network, the fusion processing of the real-time collected vehicle body longitudinal displacement data and the optical fiber strain data of the corresponding mileage segment, and the calculation of the longitudinal change degree of the foundation within the monitoring interval specifically further include:

[0095] Step S311: Based on the dynamic time warping algorithm, phase align the vehicle longitudinal displacement curve with the optical fiber strain curve of the corresponding mileage segment;

[0096] Step S312: Calculate the longitudinal deformation gradient value of the foundation within the monitoring interval based on the differential algorithm ;

[0097] The longitudinal deformation gradient value of the foundation The calculation process is:

[0098] ;

[0099] Where, For the The longitudinal deformation gradient of the monitoring surface, is the longitudinal displacement of the vehicle-mounted sensor in the corresponding section, is the cross-section spacing, Vertical strain-converted displacement calculated for the fiber optic sensing monitor group;

[0100] When this embodiment is applied, the coordinated application of the dynamic time warping algorithm and the differential algorithm realizes the deep fusion analysis of the vehicle-borne dynamic response data and the foundation static strain data, and constructs a high-precision longitudinal deformation gradient calculation model. In the spatiotemporal synchronization calibration link, due to the differences in sampling frequency and data transmission delay between the vehicle-borne displacement sensor and the distributed optical fiber sensing network, and the change in train running speed will cause a phase deviation between the vehicle-borne data time series and the line mileage mark, the dynamic time warping algorithm elastically matches the dynamic bending characteristics of the time series to phase-align the vehicle-borne longitudinal displacement curve with the optical fiber strain curve of the corresponding mileage segment. Specifically, the algorithm aims to minimize the cumulative sum of the Euclidean distance between the two curve points. By constructing a cost matrix and finding the optimal path, it solves the time-space asynchrony problem caused by factors such as vehicle acceleration, deceleration, and vibration, ensures that the vehicle-borne displacement data and the optical fiber strain data of the same monitoring section correspond in the spatiotemporal dimension, and calculates the generated foundation longitudinal deformation gradient value. , which can reflect the deformation gradient intensity within the monitoring section.

[0101] like Figure 4 As shown in FIG. 1 , as a preferred embodiment of the present invention, the multi-level threshold triggering and rechecking strategy is specifically configured as follows:

[0102] Step S401: Preset two levels of longitudinal change thresholds;

[0103] The primary change degree threshold is , the emergency change threshold is ;

[0104] Step S402: When the foundation longitudinal deformation gradient value of three consecutive sampling periods is Exceeding the primary change threshold When the regional level re-inspection instruction is triggered;

[0105] Step S403: Based on the regional re-inspection instruction, the optical fiber static level sensor group deployed in the monitoring section is controlled to measure the pressure change of each reference point in real time through the liquid level connecting pipe;

[0106] Step S404: Calculate the relative settlement of each reference point ;

[0107] The relative settlement The calculation process is:

[0108] ;

[0109] Where, is the pressure change value, is the density of the connecting fluid, Take 9.81 ;

[0110] Step S405: When the longitudinal deformation gradient value of the foundation Exceeding the emergency change threshold , triggering full-line-level real-time scanning;

[0111] It should be understood that when the foundation longitudinal deformation gradient value calculated by the system exceeds the primary change threshold for three consecutive sampling periods When the command is triggered, the regional re-inspection command is triggered immediately. This command activates the fiber optic static level sensor group deployed in the 50-200 meter monitoring section. The sensors are distributed at a distance of 5-10 meters in key areas such as the bridge-roadbed transition section and soft soil foundation. The pressure change data of each benchmark point is collected in real time through the liquid level connecting pipe. Based on the liquid column balance principle of the connecting pipe, the relative settlement of each benchmark point is calculated. If the longitudinal deformation gradient value of the foundation exceeds the emergency change threshold, the pressure change data of each benchmark point is collected in real time. , immediately launching a line-wide real-time scanning program. This program mobilizes a distributed fiber optic sensing network, onboard monitoring equipment, and fixed monitoring points along the entire railway line to conduct simultaneous inspections along the entire line. The distributed fiber optic sensing network continuously monitors ground strain with a spatial resolution of 1 meter. Onboard sensors simultaneously collect dynamic displacement data during driving. Fixed monitoring points along the line transmit real-time parameters such as ambient temperature, humidity, and groundwater level.

[0112] like Figure 5 As shown, as a preferred embodiment of the present invention, the fusion of multi-source data, based on multi-level threshold triggering and re-inspection strategy, generates and sends a ladder intelligent early warning notification, specifically including:

[0113] Step S501: building a fusion warning model including a back propagation neural network;

[0114] The input parameters of the fusion warning model include: vehicle longitudinal displacement, optical fiber strain value, liquid level pressure change rate, ambient temperature and humidity, and train speed;

[0115] Step S502: When the relative settlement of any reference point When the target threshold is exceeded, a step-by-step warning signal is generated;

[0116] And set the ballastless section threshold , ballasted section threshold ;

[0117] In ballastless sections, the stepped warning signals include:

[0118] Yellow alert: Generate and send manual inspection instructions;

[0119] Orange alert: When , a speed reduction instruction is generated and sent;

[0120] Orange alert: Generate and send an emergency stop command;

[0121] When this embodiment is applied, a back propagation neural network is used to build a fusion warning model. The input parameters of this model are multiple, including the longitudinal displacement of the vehicle, which can reflect the dynamic changes in the longitudinal direction of the vehicle body during the train's travel; the optical fiber strain value, which can capture the deformation information of the foundation; the hydraulic pressure change rate, which helps to monitor the fluctuation of the internal pressure of the foundation; the ambient temperature and humidity, because environmental factors can have a potential impact on the stability of the foundation; the train speed, the railway foundation is subjected to different forces at different speeds; in terms of settlement monitoring and threshold setting, specific technical means are used to accurately calculate the relative settlement of each reference point. Differentiated settlement thresholds are set for different track structure characteristics, and the ballastless section threshold is , ballasted section threshold . Full consideration is given to the differences in the tolerance of different track types to settlement; when the yellow warning state is triggered, a manual inspection instruction is generated and sent. This is when the settlement shows initial abnormalities but is not yet serious. A manual close-up inspection is performed to further determine the actual condition of the foundation; when the orange warning state is triggered, a speed reduction instruction is generated and sent. This means that the settlement has reached a certain level, which may affect the safe and smooth operation of the train. By reducing the speed of the train, the force on the foundation is reduced, and time is also gained for further treatment; when the red warning state is triggered, an emergency stop instruction is immediately generated and sent. This indicates that the foundation settlement is in a state that seriously threatens the safety of the train. Emergency stopping can avoid accidents to the greatest extent and protect the lives of people and the safety of equipment and property.

[0122] like Figure 6 As shown, as another preferred embodiment of the present invention, on the other hand, a railway foundation settlement management and early warning system, the system includes:

[0123] The first real-time acquisition module 100 is used to install a vehicle-mounted displacement sensor at a target position of a moving vehicle to collect the longitudinal displacement data of the vehicle body in real time during the vehicle's travel;

[0124] The target locations include the bogie axle box, the central section of the car body underframe, and the car body just above the rail contact surface;

[0125] The second real-time acquisition module 200 is used to deploy a continuous distributed optical fiber sensor monitor group and a temperature sensor in the railway line to collect continuous strain distribution data and temperature data of the railway foundation in real time;

[0126] The continuous distributed optical fiber sensor monitor group includes an optical fiber sensor network laid along the railway line;

[0127] A spatiotemporal synchronization calibration model module 300 is used to establish a spatiotemporal synchronization calibration model of the vehicle-mounted displacement sensor and the optical fiber sensing network;

[0128] The calculation module 400 is used to fuse the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage segment to calculate the longitudinal change degree of the foundation within the monitoring interval;

[0129] The control module 500 is used to set multi-level threshold triggering and rechecking strategies;

[0130] The generation and sending module 600 is used to integrate multi-source data and generate and send step-by-step intelligent early warning notifications based on multi-level threshold triggering and re-inspection strategies.

[0131] When this embodiment is applied, an on-board displacement sensor is installed at a target position of a moving vehicle. The first real-time acquisition module 100 collects the longitudinal displacement data of the vehicle body in real time during driving. A continuous distributed optical fiber sensor monitor group and a temperature sensor are deployed in the railway line. The second real-time acquisition module 200 collects the continuous strain distribution data and temperature data of the railway foundation in real time. The spatiotemporal synchronization calibration model module 300 establishes a spatiotemporal synchronization calibration model of the on-board displacement sensor and the optical fiber sensor network. The calculation module 400 fuses the real-time collected longitudinal displacement data of the vehicle body with the optical fiber strain data of the corresponding mileage section, and calculates the longitudinal change degree of the foundation within the monitoring interval. The management and control module 500 sets a multi-level threshold trigger and re-inspection strategy, fuses multi-source data, and generates and sends a step-by-step intelligent early warning notification based on the multi-level threshold trigger and re-inspection strategy.

[0132] like Figure 7 As shown, as another preferred embodiment of the present invention, the spatiotemporal synchronization calibration model module 300 specifically includes:

[0133] A mapping unit 301 is configured to establish a spatiotemporal mapping relationship based on a GPS time stamp of a traveling vehicle and a mileage mark of a route;

[0134] The synchronous compensation unit 302 is used to perform denoising on the vehicle displacement data using a Kalman filter algorithm and synchronously perform temperature compensation on the optical fiber strain data.

[0135] When this embodiment is applied, the mapping unit 301 establishes a spatiotemporal mapping relationship based on the vehicle's onboard GPS timestamp and the route mileage mark, denoises the vehicle's onboard displacement data through the Kalman filter algorithm, and the synchronous compensation unit 302 synchronously performs temperature compensation on the optical fiber strain data.

[0136] like Figure 8As shown, as another preferred embodiment of the present invention, the calculation module 400 includes:

[0137] A phase alignment unit 401 is used to phase-align the vehicle longitudinal displacement curve with the optical fiber strain curve of the corresponding mileage segment based on a dynamic time warping algorithm;

[0138] The first calculation unit 402 is used to calculate the longitudinal deformation gradient value of the foundation within the monitoring interval based on the differential algorithm .

[0139] When this embodiment is applied, based on the dynamic time warping algorithm, the phase alignment unit 401 phase-aligns the vehicle longitudinal displacement curve with the optical fiber strain curve of the corresponding mileage segment, and based on the differential algorithm, the first calculation unit 402 calculates the longitudinal deformation gradient value of the foundation within the monitoring interval. .

[0140] like Figure 9 As shown, as another preferred embodiment of the present invention, the control module 500 specifically includes:

[0141] A two-level longitudinal change degree threshold unit 501 is used to preset two-level longitudinal change degree thresholds;

[0142] The recheck unit 502 is used to check the longitudinal deformation gradient value of the foundation for three consecutive sampling periods. Exceeding the primary change threshold When the regional level re-inspection instruction is triggered;

[0143] The real-time measurement unit 503 is used to control the fiber optic static level sensor group deployed in the monitoring section based on the regional re-inspection instruction, and measure the pressure changes of each reference point in real time through the liquid level connecting pipe;

[0144] The second calculation unit 504 is used to calculate the relative settlement of each reference point ;

[0145] The full-line real-time scanning unit 505 is used to measure the longitudinal deformation gradient value of the local foundation. Exceeding the emergency change threshold , triggering full-line-level real-time scanning.

[0146] In this embodiment, when applied, the two-level longitudinal change threshold unit 501 presets two-level longitudinal change thresholds. When the longitudinal deformation gradient value of the foundation for three consecutive sampling periods is Exceeding the primary change threshold When the recheck unit 502 triggers the regional recheck instruction, based on the regional recheck instruction, the real-time measurement unit 203 controls the fiber optic static level sensor group deployed in the monitoring section to measure the pressure change of each reference point in real time through the liquid level connecting pipe. The second calculation unit 504 calculates the relative settlement of each reference point. , when the longitudinal deformation gradient value of the foundation Exceeding the emergency change threshold , the full-line level real-time scanning unit 505 triggers the full-line level real-time scanning.

[0147] like Figure 10 As shown, as another preferred embodiment of the present invention, the generating and sending module 600 specifically includes:

[0148] The fusion warning model unit 601 is used to construct a fusion warning model including a back propagation neural network;

[0149] The input parameters of the fusion warning model include: vehicle longitudinal displacement, optical fiber strain value, liquid level pressure change rate, ambient temperature and humidity, and train speed;

[0150] Generating unit 602, used to generate the relative settlement of any reference point When the target threshold is exceeded, a stepped warning signal is generated.

[0151] When this embodiment is applied, the fusion warning model unit 601 constructs a fusion warning model including a back propagation neural network. When the relative settlement of any benchmark point is When the target threshold is exceeded, the generating unit 602 generates a stepped warning signal.

[0152] The above-described embodiments of the present invention provide a method and system for managing and warning railway foundation settlement. This system establishes a three-in-one intelligent monitoring system for "vehicle-track-foundation." At the data acquisition level, high-precision on-board displacement sensors are precisely installed on the bogie axlebox, the central section of the vehicle underframe, and the vehicle body directly above the rail contact surface. These sensors, comprising a MEMS inertial measurement unit (MEMS) with a sampling frequency ≥100Hz and a Beidou differential positioning module with centimeter-level accuracy, capture vehicle longitudinal displacement, pitch angle, and acceleration data in real time at a high-frequency interval of ≤50ms, accurately reflecting the dynamic response of the vehicle during operation. Simultaneously, two single-mode optical fibers are laid parallel to each other at a depth of 0.3-0.5m below the roadbed surface on both sides of the railway line, forming a distributed fiber optic sensing network with a spacing of 50-100m. Leveraging BOTDA technology, this network enables continuous strain data acquisition with a spatial resolution of ≤1m, comprehensively capturing foundation status information and eliminating temperature interference on fiber optic strain measurements. In the data processing and analysis phase, a spatiotemporal synchronization calibration model is established based on the vehicle-mounted GPS timestamp and line mileage markers. The Kalman filter algorithm is used to denoise the vehicle-mounted displacement data, and the dynamic time warping algorithm is used to phase-align the vehicle-mounted longitudinal displacement curve with the fiber optic strain curve. The longitudinal change degree of the foundation within the monitoring interval is calculated, achieving deep integration of vehicle-ground data. Two-level longitudinal change thresholds and corresponding regional and full-line re-inspection strategies are set. Relative settlement is calculated using a fiber optic static level sensor group based on the principle of liquid column equilibrium in a connected tube. A multi-source data fusion early warning model is constructed based on the BP neural network. Coupled analysis is performed on multiple parameters such as vehicle-mounted longitudinal displacement, fiber optic strain value, and liquid level pressure change rate. Three-level yellow, orange, and red warning signals are generated based on the different safety thresholds of ballastless and ballasted tracks. The warning signals are then linked to the railway dispatching and operation and maintenance systems to achieve intelligent management of the entire process from monitoring to disposal. This method and system establish a "vehicle-track-foundation" three-in-one intelligent monitoring system, significantly improving the spatiotemporal resolution and accuracy of railway foundation settlement monitoring. Multi-level thresholds and a recheck mechanism reduce false alarms and missed alarms, while a stepped early warning system enables risk-based management and control, effectively ensuring train safety. The intelligent early warning system integrates railway dispatching and operations, improving emergency response efficiency.

[0153] In order to enable the above-mentioned method and system to be loaded and run smoothly, in addition to the various modules mentioned above, the system may also include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, processors and memories, etc.

[0154] The processor may be a central processing unit, other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the system, connecting various components using various interfaces and lines.

[0155] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0157] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A railway foundation settlement management and early warning method, characterized in that: The method comprises: Installing on-board displacement sensors at targeted locations on the moving vehicle to collect real-time longitudinal displacement data of the vehicle body during driving. The targeted locations include the bogie axle box, the central section of the vehicle body underframe, and the vehicle body directly above the rail contact surface; Deploy a continuous distributed optical fiber sensor monitor group and temperature sensors within the railway line to collect continuous strain distribution data and temperature data of the railway foundation in real time. The continuous distributed optical fiber sensor monitor group includes an optical fiber sensor network laid along the railway line; A spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the fiber optic sensing network is established. The real-time collected vehicle body longitudinal displacement data is fused with the fiber optic strain data of the corresponding mileage segment to calculate the longitudinal change degree of the foundation within the monitoring interval. Set up multi-level threshold triggering and rechecking strategies; By integrating multi-source data and based on multi-level threshold triggering and re-inspection strategies, it generates and sends stepped intelligent early warning notifications.

2. The railway foundation settlement management and early warning method according to claim 1 is characterized in that: The establishment of a spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the optical fiber sensing network, fusing the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage segment, and calculating the longitudinal change degree of the foundation within the monitoring interval specifically includes: Establish a spatiotemporal mapping relationship based on the GPS timestamps on the vehicles and the mileage marks on the routes; The vehicle displacement data is de-noised using the Kalman filter algorithm, and the optical fiber strain data is temperature compensated simultaneously; The compensated optical fiber strain value The calculation process is: ； Where, is the original optical fiber strain measurement value without temperature compensation, is the thermal expansion coefficient of the optical fiber, is the real-time temperature change.

3. The railway foundation settlement management and early warning method according to claim 1, characterized in that: The establishment of a spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the optical fiber sensing network, fusing the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage segment, and calculating the longitudinal change degree of the foundation within the monitoring interval specifically includes: Based on the dynamic time warping algorithm, the vehicle longitudinal displacement curve is phase-aligned with the optical fiber strain curve of the corresponding mileage segment; Based on the differential algorithm, the longitudinal deformation gradient value of the foundation within the monitoring area is calculated ; The longitudinal deformation gradient value of the foundation The calculation process is: ； Where, For the The longitudinal deformation gradient of the monitoring surface, is the longitudinal displacement of the vehicle-mounted sensor in the corresponding section, is the cross-section spacing, Vertical strain-converted displacement calculated for the fiber optic sensing monitor set.

4. The railway foundation settlement management and early warning method according to claim 1, characterized in that: The multi-level threshold trigger and recheck strategy setting specifically includes: Two levels of longitudinal change thresholds are preset, the primary change threshold is , the emergency change threshold is ; When the longitudinal deformation gradient value of the foundation is Exceeding the primary change threshold When the regional level re-inspection instruction is triggered; Based on the regional re-inspection instructions, the fiber optic static level sensor group deployed in the monitoring section is controlled to measure the pressure changes of each reference point in real time through the liquid level connecting pipe; Calculate the relative settlement of each benchmark point ; The relative settlement The calculation process is: ； Where, is the pressure change value, is the density of the connecting fluid, Take 9.81 ; When the foundation longitudinal deformation gradient value Exceeding the emergency change threshold , triggering full-line-level real-time scanning.

5. The railway foundation settlement management and early warning method according to claim 1, characterized in that: The fusion of multi-source data, based on multi-level threshold triggering and re-inspection strategies, generates and sends step-by-step intelligent early warning notifications, specifically including: Construct a fusion warning model including a back-propagation neural network. The input parameters of the fusion warning model include: vehicle longitudinal displacement, optical fiber strain value, liquid level pressure change rate, ambient temperature and humidity, and train speed; When the relative settlement of any benchmark point When the target threshold is exceeded, a step-by-step warning signal is generated and a ballastless section threshold is set. , ballasted section threshold ; In ballastless sections, the stepped warning signals include: Yellow alert: Generate and send manual inspection instructions; Orange alert: When , a speed reduction instruction is generated and sent; Orange alert: Generate and send an emergency stop command.

6. A railway foundation settlement management and early warning system, characterized in that: The railway foundation settlement management and early warning method according to any one of claims 1 to 5 is applied, wherein the system comprises: The first real-time acquisition module is used to install a vehicle-mounted displacement sensor at a target position of a moving vehicle to collect the longitudinal displacement data of the vehicle body in real time during the vehicle's driving process; The target locations include the bogie axle box, the central section of the car body underframe, and the car body just above the rail contact surface; The second real-time acquisition module is used to deploy a continuous distributed optical fiber sensor monitor group and temperature sensors within the railway line to collect continuous strain distribution data and temperature data of the railway foundation in real time; The continuous distributed optical fiber sensor monitor group includes an optical fiber sensor network laid along the railway line; The spatiotemporal synchronization calibration model module is used to establish a spatiotemporal synchronization calibration model for the vehicle-mounted displacement sensor and the optical fiber sensing network; The calculation module is used to integrate the real-time collected vehicle body longitudinal displacement data with the optical fiber strain data of the corresponding mileage section to calculate the longitudinal change degree of the foundation within the monitoring area; The control module is used to set multi-level threshold triggers and re-inspection strategies; Generate and send modules to integrate multi-source data, generate and send step-by-step intelligent early warning notifications based on multi-level threshold triggering and re-inspection strategies.

7. The railway foundation settlement management and early warning system according to claim 6, characterized in that: The spatiotemporal synchronization calibration model module specifically includes: A mapping unit, configured to establish a spatiotemporal mapping relationship based on a GPS time stamp of a traveling vehicle and a mileage mark of a route; The synchronous compensation unit is used to perform denoising on the vehicle displacement data through the Kalman filter algorithm and synchronously perform temperature compensation on the optical fiber strain data.

8. The railway foundation settlement management and early warning system according to claim 6, characterized in that: The calculation module includes: Phase alignment unit, used to align the vehicle longitudinal displacement curve with the optical fiber strain curve of the corresponding mileage segment based on the dynamic time warping algorithm; The first calculation unit is used to calculate the longitudinal deformation gradient value of the foundation within the monitoring interval based on the differential algorithm .

9. The railway foundation settlement management and early warning system according to claim 6, characterized in that: The control module specifically includes: A two-level longitudinal change degree threshold unit is used to preset two-level longitudinal change degree thresholds; Recheck unit, used for the longitudinal deformation gradient value of the foundation for three consecutive sampling periods Exceeding the primary change threshold When the regional level re-inspection instruction is triggered; The real-time measurement unit is used to control the fiber optic static level sensor group deployed in the monitoring section based on the regional re-inspection instructions, and measure the pressure changes of each reference point in real time through the liquid level connecting pipe; The second calculation unit is used to calculate the relative settlement of each benchmark point ; Full-line real-time scanning unit, used to measure the longitudinal deformation gradient value of the local foundation Exceeding the emergency change threshold , triggering full-line-level real-time scanning.

10. The railway foundation settlement management and early warning system according to claim 6, characterized in that: The generating and sending module specifically includes: A fusion warning model unit, used to construct a fusion warning model including a back-propagation neural network; The input parameters of the fusion warning model include: vehicle longitudinal displacement, optical fiber strain value, liquid level pressure change rate, ambient temperature and humidity, and train speed; Generate units for relative settlement of any benchmark point When the target threshold is exceeded, a stepped warning signal is generated.

Images